© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 28129
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     이전
    -0.07
     [$
    -0.07
     흐
    -0.07
     hyp
    -0.06
     Pow
    -0.06
    阶段
    -0.06
     구
    -0.06
     accountable
    -0.06
     linked
    -0.06
     cấp
    -0.06
    POSITIVE LOGITS
    10
    0.07
    ennai
    0.06
    .btnCancel
    0.06
    _AUTO
    0.06
     pretend
    0.06
    essaging
    0.06
    _principal
    0.06
     bilder
    0.06
    bung
    0.06
     Ventura
    0.06
    Activations Density 0.013%

    No Known Activations